红外卫星云图的多值自适应分割

Multiple value self-adapt segmentation of infrared satellite cloud image

云的形状千变万化,难以分割和识别。本文利用数学形态学图像分析方法,设计并实现了红外卫星云图的预处理和多值自适应分割。通过该分割可以自动将云图中相对面积较大且温度较低的不多于5块的云从整张图上分割出来,这为识别工作奠定了基础。运行实例表明,该分割方法具有很好的自适应性和实用性。

It is difficult to segment and recognize clouds from the infrared satellite cloud images because of its various shapes. Using mathematical morphology, this paper fulfills the pre-processing and multiple value self-adapt segmentation. The clouds that are larger and have lower temperature can be segmented from the images through the automatical procedure, which is the base of recognition. Example shows that the segmentation method has self-adaptability and practicability.